·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
GAGPO: Generalized Advantage Grouped Policy Optimization3h◆UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems3h◆Orchestra-o1: Omnimodal Agent Orchestration3h◆Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher3h◆WorkBench Revisited: Workplace Agents Two Years On3h◆Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP3h◆YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications3h◆MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis3h◆A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale3h◆Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL3h◆SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing3h◆CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning3h◆Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows3h◆An Agentic Retrieval Framework for Autonomous Context-Aware Data Quality Assessment3h◆Aligning Quantum Operators with Large Language Models3h◆Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response3h◆When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation3h◆Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning3h◆Clay-CNN Hybrids: Leveraging Geo-Foundational Models as Auxiliary Context for Landslide Detection3h◆FEMOT: Multi-Object Tracking using Frame and Event Cameras3h◆GAGPO: Generalized Advantage Grouped Policy Optimization3h◆UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems3h◆Orchestra-o1: Omnimodal Agent Orchestration3h◆Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher3h◆WorkBench Revisited: Workplace Agents Two Years On3h◆Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP3h◆YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications3h◆MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis3h◆A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale3h◆Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL3h◆SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing3h◆CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning3h◆Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows3h◆An Agentic Retrieval Framework for Autonomous Context-Aware Data Quality Assessment3h◆Aligning Quantum Operators with Large Language Models3h◆Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response3h◆When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation3h◆Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning3h◆Clay-CNN Hybrids: Leveraging Geo-Foundational Models as Auxiliary Context for Landslide Detection3h◆FEMOT: Multi-Object Tracking using Frame and Event Cameras3h◆
News/MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents
arxiv
PublishedMay 22, 2026 at 4:00 AM

MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.15774v2 Announce Type: replace Abstract: Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent behaviors. Existi

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivGAGPO: Generalized Advantage Grouped Policy Optimization3harxivUP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems3harxivOrchestra-o1: Omnimodal Agent Orchestration3harxivHybrid Open-Ended Tri-Evolution Makes Better Deep Researcher3h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews